Single Layer Perceptons.ipynb

single-layer-perceptons.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyNzFDttozebdqW0Il57cWon",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/omayib/2662984488f82f5880c6fe9636dcd09b/single-layer-perceptons.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import random\n",
        "from decimal import Decimal"
      ],
      "metadata": {
        "id": "DuKzI8C0KfKZ"
      },
      "execution_count": 106,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "MNS3YQPgm3ew"
      },
      "execution_count": 106,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": 107,
      "metadata": {
        "id": "pc-GrtQ5IJek"
      },
      "outputs": [],
      "source": [
        "data = [\n",
        "    [1, 5.1, 3.5, 1.4, 0.2],\n",
        "    [1, 4.9, 3.0, 1.4, 0.2],\n",
        "    [1, 4.7, 3.2, 1.3, 0.2],\n",
        "    [1, 4.6, 3.1, 1.5, 0.2],\n",
        "    [1, 5.0, 3.6, 1.4, 0.2],\n",
        "    [1, 5.4, 3.9, 1.7, 0.4],\n",
        "    [1, 4.6, 3.4, 1.4, 0.3],\n",
        "    [1, 5.0, 3.4, 1.5, 0.2],\n",
        "    [1, 4.4, 2.9, 1.4, 0.2],\n",
        "    [1, 4.9, 3.1, 1.5, 0.1],\n",
        "    [1, 5.4, 3.7, 1.5, 0.2],\n",
        "    [1, 4.8, 3.4, 1.6, 0.2],\n",
        "    [1, 4.8, 3.0, 1.4, 0.1],\n",
        "    [1, 4.3, 3.0, 1.1, 0.1],\n",
        "    [1, 5.8, 4.0, 1.2, 0.2],\n",
        "    [1, 5.7, 4.4, 1.5, 0.4],\n",
        "    [1, 5.4, 3.9, 1.3, 0.4],\n",
        "    [1, 5.1, 3.5, 1.4, 0.3],\n",
        "    [1, 5.7, 3.8, 1.7, 0.3],\n",
        "    [1, 5.1, 3.8, 1.5, 0.3],\n",
        "    [1, 5.4, 3.4, 1.7, 0.2],\n",
        "    [1, 5.1, 3.7, 1.5, 0.4],\n",
        "    [1, 4.6, 3.6, 1.0, 0.2],\n",
        "    [1, 5.1, 3.3, 1.7, 0.5],\n",
        "    [1, 4.8, 3.4, 1.9, 0.2],\n",
        "    [1, 5.0, 3.0, 1.6, 0.2],\n",
        "    [1, 5.0, 3.4, 1.6, 0.4],\n",
        "    [1, 5.2, 3.5, 1.5, 0.2],\n",
        "    [1, 5.2, 3.4, 1.4, 0.2],\n",
        "    [1, 4.7, 3.2, 1.6, 0.2],\n",
        "    [1, 4.8, 3.1, 1.6, 0.2],\n",
        "    [1, 5.4, 3.4, 1.5, 0.4],\n",
        "    [1, 5.2, 4.1, 1.5, 0.1],\n",
        "    [1, 5.5, 4.2, 1.4, 0.2],\n",
        "    [1, 4.9, 3.1, 1.5, 0.1],\n",
        "    [1, 5.0, 3.2, 1.2, 0.2],\n",
        "    [1, 5.5, 3.5, 1.3, 0.2],\n",
        "    [1, 4.9, 3.1, 1.5, 0.1],\n",
        "    [1, 4.4, 3.0, 1.3, 0.2],\n",
        "    [1, 5.1, 3.4, 1.5, 0.2],\n",
        "    [1, 5.0, 3.5, 1.3, 0.3],\n",
        "    [1, 4.5, 2.3, 1.3, 0.3],\n",
        "    [1, 4.4, 3.2, 1.3, 0.2],\n",
        "    [1, 5.0, 3.5, 1.6, 0.6],\n",
        "    [1, 5.1, 3.8, 1.9, 0.4],\n",
        "    [1, 4.8, 3.0, 1.4, 0.3],\n",
        "    [1, 5.1, 3.8, 1.6, 0.2],\n",
        "    [1, 4.6, 3.2, 1.4, 0.2],\n",
        "    [1, 5.3, 3.7, 1.5, 0.2],\n",
        "    [1, 5.0, 3.3, 1.4, 0.2],\n",
        "    [1, 7.0, 3.2, 4.7, 1.4],\n",
        "    [1, 6.4, 3.2, 4.5, 1.5],\n",
        "    [1, 6.9, 3.1, 4.9, 1.5],\n",
        "    [1, 5.5, 2.3, 4.0, 1.3],\n",
        "    [1, 6.5, 2.8, 4.6, 1.5],\n",
        "    [1, 5.7, 2.8, 4.5, 1.3],\n",
        "    [1, 6.3, 3.3, 4.7, 1.6],\n",
        "    [1, 4.9, 2.4, 3.3, 1.0],\n",
        "    [1, 6.6, 2.9, 4.6, 1.3],\n",
        "    [1, 5.2, 2.7, 3.9, 1.4],\n",
        "    [1, 5.0, 2.0, 3.5, 1.0],\n",
        "    [1, 5.9, 3.0, 4.2, 1.5],\n",
        "    [1, 6.0, 2.2, 4.0, 1.0],\n",
        "    [1, 6.1, 2.9, 4.7, 1.4],\n",
        "    [1, 5.6, 2.9, 3.6, 1.3],\n",
        "    [1, 6.7, 3.1, 4.4, 1.4],\n",
        "    [1, 5.6, 3.0, 4.5, 1.5],\n",
        "    [1, 5.8, 2.7, 4.1, 1.0],\n",
        "    [1, 6.2, 2.2, 4.5, 1.5],\n",
        "    [1, 5.6, 2.5, 3.9, 1.1],\n",
        "    [1, 5.9, 3.2, 4.8, 1.8],\n",
        "    [1, 6.1, 2.8, 4.0, 1.3],\n",
        "    [1, 6.3, 2.5, 4.9, 1.5],\n",
        "    [1, 6.1, 2.8, 4.7, 1.2],\n",
        "    [1, 6.4, 2.9, 4.3, 1.3],\n",
        "    [1, 6.6, 3.0, 4.4, 1.4],\n",
        "    [1, 6.8, 2.8, 4.8, 1.4],\n",
        "    [1, 6.7, 3.0, 5.0, 1.7],\n",
        "    [1, 6.0, 2.9, 4.5, 1.5],\n",
        "    [1, 5.7, 2.6, 3.5, 1.0],\n",
        "    [1, 5.5, 2.4, 3.8, 1.1],\n",
        "    [1, 5.5, 2.4, 3.7, 1.0],\n",
        "    [1, 5.8, 2.7, 3.9, 1.2],\n",
        "    [1, 6.0, 2.7, 5.1, 1.6],\n",
        "    [1, 5.4, 3.0, 4.5, 1.5],\n",
        "    [1, 6.0, 3.4, 4.5, 1.6],\n",
        "    [1, 6.7, 3.1, 4.7, 1.5],\n",
        "    [1, 6.3, 2.3, 4.4, 1.3],\n",
        "    [1, 5.6, 3.0, 4.1, 1.3],\n",
        "    [1, 5.5, 2.5, 4.0, 1.3],\n",
        "    [1, 5.5, 2.6, 4.4, 1.2],\n",
        "    [1, 6.1, 3.0, 4.6, 1.4],\n",
        "    [1, 5.8, 2.6, 4.0, 1.2],\n",
        "    [1, 5.0, 2.3, 3.3, 1.0],\n",
        "    [1, 5.6, 2.7, 4.2, 1.3],\n",
        "    [1, 5.7, 3.0, 4.2, 1.2],\n",
        "    [1, 5.7, 2.9, 4.2, 1.3],\n",
        "    [1, 6.2, 2.9, 4.3, 1.3],\n",
        "    [1, 5.1, 2.5, 3.0, 1.1],\n",
        "    [1, 5.7, 2.8, 4.1, 1.3]\n",
        "]\n",
        "\n",
        "weights = [[0.5,0.5,0.5,0.5,0.5]]\n",
        "targets = [\n",
        "    0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
        "    0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
        "    0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
        "    0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
        "    0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
        "    1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
        "    1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
        "    1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
        "    1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
        "    1, 1, 1, 1, 1, 1, 1, 1, 1, 1\n",
        "]\n",
        "\n",
        "learning_rate=0.1"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset = list(zip(data, targets))\n",
        "# random.shuffle(dataset)\n",
        "print(len(dataset))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LtaQIJFIlFeA",
        "outputId": "7865191c-4210-4677-8e95-b0acae05ce44"
      },
      "execution_count": 108,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "100\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def dotproduct_z(vec1,vec2):\n",
        "  product = 0\n",
        "  for i in range(len(vec1)):\n",
        "    product += vec1[i]*vec2[i]\n",
        "  return product\n",
        "\n",
        "prediction = dotproduct_z(data[0],weights[0])\n",
        "print(prediction)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-lKnCH_XJ10z",
        "outputId": "524178e5-524f-4222-eb8b-13f04a4e3b60"
      },
      "execution_count": 109,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "5.6\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def sigmoid(x):\n",
        "  return 1/(1+np.exp(-x))\n",
        "\n",
        "prediction_normalized = sigmoid(prediction)\n",
        "print(prediction_normalized)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bLksdBSeKRPJ",
        "outputId": "9808d456-6c62-4311-c5e7-87c9a6f3fc00"
      },
      "execution_count": 110,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.9963157601005641\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def delta_bias(prediction,target,input):\n",
        "  return 2*(prediction-target)*(1-prediction)*prediction\n",
        "\n",
        "print(delta_bias(prediction_normalized,targets[0],data[0][0]))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MtCFycv1Or1i",
        "outputId": "b74bf17f-a6ad-4102-fcf9-42d854ed3295"
      },
      "execution_count": 111,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.0073142853212969676\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def delta_weight(prediction,target,input):\n",
        "  return 2*(prediction-target)*(1-prediction)*prediction*input\n",
        "\n",
        "dweight=delta_weight(prediction_normalized,targets[0],data[0][1])\n",
        "print(dweight)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "oqFJwzHDbRJm",
        "outputId": "c33ffeff-5faa-4096-d83e-1a9d30c0985b"
      },
      "execution_count": 112,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.03730285513861453\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def update_weight(prev_weight,delta_weight):\n",
        "  return prev_weight-learning_rate*delta_weight\n",
        "\n",
        "print(update_weight(weights[0][0],dweight))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7mCzA7Ftb35z",
        "outputId": "c8376f36-c036-4d3d-cbe8-b3c16de1e092"
      },
      "execution_count": 113,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.49626971448613855\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def sum_square_error(prediction,target):\n",
        "  return (prediction-target)**2\n",
        "\n",
        "print(sum_square_error(prediction_normalized,targets[0]))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2lsKCjMiXq0Z",
        "outputId": "fea5e7ed-ad46-4cb9-b697-e71e7ad05ffa"
      },
      "execution_count": 114,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.9926450938247648\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "split_at_index=int(0.8*len(dataset))\n",
        "print(split_at_index)\n",
        "train_dataset = dataset[:split_at_index]\n",
        "test_dataset = dataset[split_at_index:]\n",
        "print(train_dataset)\n",
        "print(test_dataset)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VarlpsasbkyZ",
        "outputId": "45e448ca-bea2-4f4a-fc48-7ed9f097170f"
      },
      "execution_count": 115,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "80\n",
            "[([1, 5.1, 3.5, 1.4, 0.2], 0), ([1, 4.9, 3.0, 1.4, 0.2], 0), ([1, 4.7, 3.2, 1.3, 0.2], 0), ([1, 4.6, 3.1, 1.5, 0.2], 0), ([1, 5.0, 3.6, 1.4, 0.2], 0), ([1, 5.4, 3.9, 1.7, 0.4], 0), ([1, 4.6, 3.4, 1.4, 0.3], 0), ([1, 5.0, 3.4, 1.5, 0.2], 0), ([1, 4.4, 2.9, 1.4, 0.2], 0), ([1, 4.9, 3.1, 1.5, 0.1], 0), ([1, 5.4, 3.7, 1.5, 0.2], 0), ([1, 4.8, 3.4, 1.6, 0.2], 0), ([1, 4.8, 3.0, 1.4, 0.1], 0), ([1, 4.3, 3.0, 1.1, 0.1], 0), ([1, 5.8, 4.0, 1.2, 0.2], 0), ([1, 5.7, 4.4, 1.5, 0.4], 0), ([1, 5.4, 3.9, 1.3, 0.4], 0), ([1, 5.1, 3.5, 1.4, 0.3], 0), ([1, 5.7, 3.8, 1.7, 0.3], 0), ([1, 5.1, 3.8, 1.5, 0.3], 0), ([1, 5.4, 3.4, 1.7, 0.2], 0), ([1, 5.1, 3.7, 1.5, 0.4], 0), ([1, 4.6, 3.6, 1.0, 0.2], 0), ([1, 5.1, 3.3, 1.7, 0.5], 0), ([1, 4.8, 3.4, 1.9, 0.2], 0), ([1, 5.0, 3.0, 1.6, 0.2], 0), ([1, 5.0, 3.4, 1.6, 0.4], 0), ([1, 5.2, 3.5, 1.5, 0.2], 0), ([1, 5.2, 3.4, 1.4, 0.2], 0), ([1, 4.7, 3.2, 1.6, 0.2], 0), ([1, 4.8, 3.1, 1.6, 0.2], 0), ([1, 5.4, 3.4, 1.5, 0.4], 0), ([1, 5.2, 4.1, 1.5, 0.1], 0), ([1, 5.5, 4.2, 1.4, 0.2], 0), ([1, 4.9, 3.1, 1.5, 0.1], 0), ([1, 5.0, 3.2, 1.2, 0.2], 0), ([1, 5.5, 3.5, 1.3, 0.2], 0), ([1, 4.9, 3.1, 1.5, 0.1], 0), ([1, 4.4, 3.0, 1.3, 0.2], 0), ([1, 5.1, 3.4, 1.5, 0.2], 0), ([1, 5.0, 3.5, 1.3, 0.3], 0), ([1, 4.5, 2.3, 1.3, 0.3], 0), ([1, 4.4, 3.2, 1.3, 0.2], 0), ([1, 5.0, 3.5, 1.6, 0.6], 0), ([1, 5.1, 3.8, 1.9, 0.4], 0), ([1, 4.8, 3.0, 1.4, 0.3], 0), ([1, 5.1, 3.8, 1.6, 0.2], 0), ([1, 4.6, 3.2, 1.4, 0.2], 0), ([1, 5.3, 3.7, 1.5, 0.2], 0), ([1, 5.0, 3.3, 1.4, 0.2], 0), ([1, 7.0, 3.2, 4.7, 1.4], 1), ([1, 6.4, 3.2, 4.5, 1.5], 1), ([1, 6.9, 3.1, 4.9, 1.5], 1), ([1, 5.5, 2.3, 4.0, 1.3], 1), ([1, 6.5, 2.8, 4.6, 1.5], 1), ([1, 5.7, 2.8, 4.5, 1.3], 1), ([1, 6.3, 3.3, 4.7, 1.6], 1), ([1, 4.9, 2.4, 3.3, 1.0], 1), ([1, 6.6, 2.9, 4.6, 1.3], 1), ([1, 5.2, 2.7, 3.9, 1.4], 1), ([1, 5.0, 2.0, 3.5, 1.0], 1), ([1, 5.9, 3.0, 4.2, 1.5], 1), ([1, 6.0, 2.2, 4.0, 1.0], 1), ([1, 6.1, 2.9, 4.7, 1.4], 1), ([1, 5.6, 2.9, 3.6, 1.3], 1), ([1, 6.7, 3.1, 4.4, 1.4], 1), ([1, 5.6, 3.0, 4.5, 1.5], 1), ([1, 5.8, 2.7, 4.1, 1.0], 1), ([1, 6.2, 2.2, 4.5, 1.5], 1), ([1, 5.6, 2.5, 3.9, 1.1], 1), ([1, 5.9, 3.2, 4.8, 1.8], 1), ([1, 6.1, 2.8, 4.0, 1.3], 1), ([1, 6.3, 2.5, 4.9, 1.5], 1), ([1, 6.1, 2.8, 4.7, 1.2], 1), ([1, 6.4, 2.9, 4.3, 1.3], 1), ([1, 6.6, 3.0, 4.4, 1.4], 1), ([1, 6.8, 2.8, 4.8, 1.4], 1), ([1, 6.7, 3.0, 5.0, 1.7], 1), ([1, 6.0, 2.9, 4.5, 1.5], 1), ([1, 5.7, 2.6, 3.5, 1.0], 1)]\n",
            "[([1, 5.5, 2.4, 3.8, 1.1], 1), ([1, 5.5, 2.4, 3.7, 1.0], 1), ([1, 5.8, 2.7, 3.9, 1.2], 1), ([1, 6.0, 2.7, 5.1, 1.6], 1), ([1, 5.4, 3.0, 4.5, 1.5], 1), ([1, 6.0, 3.4, 4.5, 1.6], 1), ([1, 6.7, 3.1, 4.7, 1.5], 1), ([1, 6.3, 2.3, 4.4, 1.3], 1), ([1, 5.6, 3.0, 4.1, 1.3], 1), ([1, 5.5, 2.5, 4.0, 1.3], 1), ([1, 5.5, 2.6, 4.4, 1.2], 1), ([1, 6.1, 3.0, 4.6, 1.4], 1), ([1, 5.8, 2.6, 4.0, 1.2], 1), ([1, 5.0, 2.3, 3.3, 1.0], 1), ([1, 5.6, 2.7, 4.2, 1.3], 1), ([1, 5.7, 3.0, 4.2, 1.2], 1), ([1, 5.7, 2.9, 4.2, 1.3], 1), ([1, 6.2, 2.9, 4.3, 1.3], 1), ([1, 5.1, 2.5, 3.0, 1.1], 1), ([1, 5.7, 2.8, 4.1, 1.3], 1)]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def prediction_output(prediction):\n",
        "  return 1 if prediction>0.5 else 0"
      ],
      "metadata": {
        "id": "VOWlwWJxQdpW"
      },
      "execution_count": 116,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "jamL1zY6QyQ_"
      },
      "execution_count": 116,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Train the weight\n",
        "dweights =[]\n",
        "weight=[0.5,0.5,0.5,0.5,0.5] #put initial weight for default\n",
        "iterasi = 5\n",
        "errors, y_true,y_score,y_pred,acc=[],[],[],[],[]\n",
        "\n",
        "def evaluasi():\n",
        "  y_true_arr = np.array(y_true, dtype=np.int16)\n",
        "  y_score_arr = np.array(y_score, dtype=np.float32)\n",
        "  y_pred_arr = np.array(y_pred, dtype=np.int16)\n",
        "\n",
        "\n",
        "  tp = int(np.sum((y_pred_arr==1)& (y_true_arr==1)))\n",
        "  tn = int(np.sum((y_pred_arr==0)& (y_true_arr==0)))\n",
        "  fp = int(np.sum((y_pred_arr==1)& (y_true_arr==0)))\n",
        "  fn = int(np.sum((y_pred_arr==0)& (y_true_arr==1)))\n",
        "\n",
        "  accuracy  = (tp+tn)/len(y_true)\n",
        "  precision =  tp/(tp+fp) if (tp+fp)>0 else 0\n",
        "  recall    =  tp/(tp+fn) if (tp+fn)>0 else 0\n",
        "  f1_score  =  2*precision*recall/(precision+recall) if (precision+recall)>0 else 0\n",
        "\n",
        "  # print(f\"accuracy {accuracy}\")\n",
        "  # print(f\"precision {precision}\")\n",
        "  # print(f\"recall {recall}\")\n",
        "  # print(f\"f1_score {f1_score}\")\n",
        "  return accuracy\n",
        "\n",
        "akurasi=[]\n",
        "for putaran in range(iterasi):\n",
        "  for i in range(len(train_dataset)):\n",
        "    # print(f\"===== putaran ke {putaran} data  ke {i} ===========\")\n",
        "    input,target=train_dataset[i]\n",
        "    # print(f\"weight {weight}\")\n",
        "    prediction = dotproduct_z(input,weight)\n",
        "    prediction_normalized = sigmoid(prediction)\n",
        "    prediction_label = prediction_output(prediction_normalized)\n",
        "    # print(f\"prediction_normalized {prediction_normalized}\")\n",
        "    error = sum_square_error(prediction_normalized,target)\n",
        "    w  = []\n",
        "    for j in  range(len(input)):\n",
        "      dweight=delta_weight(prediction_normalized,target,input[j])\n",
        "      dweights.append(dweight)\n",
        "      updated_weight=update_weight(weight[j],dweight)\n",
        "      w.append(updated_weight)\n",
        "    weight=w\n",
        "    # print(f\"error {error}\")\n",
        "    errors.append(error)\n",
        "    #=== evaluate\n",
        "    score = prediction\n",
        "    y_true.append(target)\n",
        "    y_score.append(score)\n",
        "    y_pred.append(prediction_label)\n",
        "    acc=evaluasi()\n",
        "    akurasi.append(acc)\n",
        "\n",
        "\n",
        "xpoints = np.array(range(len(errors)))\n",
        "ypoints = np.array(errors)\n",
        "plt.plot(xpoints,ypoints)\n",
        "plt.show()\n",
        "\n",
        "xpoints = np.array(range(len(akurasi)))\n",
        "ypoints = np.array(akurasi)\n",
        "plt.plot(xpoints,ypoints)\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 843
        },
        "id": "lqqUy8fbneUu",
        "outputId": "904305d8-b2bc-489b-ed4a-fee4d3654637",
        "collapsed": true
      },
      "execution_count": 117,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "test_errors=[]\n",
        "for i in range(len(test_dataset)):\n",
        "  data,target=test_dataset[i]\n",
        "  prediction = dotproduct_z(data,weight)\n",
        "  prediction_normalized = sigmoid(prediction)\n",
        "  error = sum_square_error(prediction_normalized,target)\n",
        "  test_errors.append(Decimal(error))\n",
        "  print(f\" prediction_normalized {prediction_normalized}\")\n",
        "  print(f\" error {Decimal(error)}\")\n",
        "xpoints = np.array(range(len(test_errors)))\n",
        "ypoints = np.array(test_errors)\n",
        "plt.plot(xpoints,ypoints)\n",
        "plt.show()"
      ],
      "metadata": {
        "id": "ZXH4HjUAl4dX",
        "outputId": "c0be241d-5251-4a0a-cb08-474db2cd1b11",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        }
      },
      "execution_count": 118,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            " prediction_normalized 0.9510703629110923\n",
            " error 0.002394109385652216058504304641019189148209989070892333984375\n",
            " prediction_normalized 0.9410319517156299\n",
            " error 0.0034772307184678008691591788448249644716270267963409423828125\n",
            " prediction_normalized 0.9503799674652224\n",
            " error 0.0024621476287523921984423669329089534585364162921905517578125\n",
            " prediction_normalized 0.9900381348014788\n",
            " error 0.00009923875823350698788249957260632072575390338897705078125\n",
            " prediction_normalized 0.9793949757941194\n",
            " error 0.000424567022524926195037320297842597938142716884613037109375\n",
            " prediction_normalized 0.9736229758388676\n",
            " error 0.000695747403596963065290637029391973555902950465679168701171875\n",
            " prediction_normalized 0.9758040047154135\n",
            " error 0.0005854461878117317615022319188256005872972309589385986328125\n",
            " prediction_normalized 0.9745881743433348\n",
            " error 0.000645760883204748808127104720000488669029437005519866943359375\n",
            " prediction_normalized 0.9602878371528089\n",
            " error 0.0015770558780018287432789225732676641200669109821319580078125\n",
            " prediction_normalized 0.965034000332922\n",
            " error 0.0012226211327181009565212566059244636562652885913848876953125\n",
            " prediction_normalized 0.9745732363281335\n",
            " error 0.00064652031082494849922870372438410413451492786407470703125\n",
            " prediction_normalized 0.9759775576934059\n",
            " error 0.000577077734373642793098968528653358589508570730686187744140625\n",
            " prediction_normalized 0.957312805846739\n",
            " error 0.0018221965446782047680363003649972597486339509487152099609375\n",
            " prediction_normalized 0.9235927479197066\n",
            " error 0.005838068170461503496315724959231374668888747692108154296875\n",
            " prediction_normalized 0.9686615148627843\n",
            " error 0.00098210065069548996806447771490411469130776822566986083984375\n",
            " prediction_normalized 0.9604319856139373\n",
            " error 0.00156562776245566651935059443445652505033649504184722900390625\n",
            " prediction_normalized 0.9649922397053836\n",
            " error 0.0012255432808453196012743457998794838204048573970794677734375\n",
            " prediction_normalized 0.964308670237327\n",
            " error 0.00127387102022786559418765506279669352807104587554931640625\n",
            " prediction_normalized 0.8927649901230049\n",
            " error 0.01149934734331923245898021690436507924459874629974365234375\n",
            " prediction_normalized 0.9625476854874851\n",
            " error 0.0014026758623443304208056048310027108527719974517822265625\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}